A Survey on Blockchain-Based Federated Learning and Data Privacy

Federated learning is a decentralized machine learning paradigm that allows multiple clients to collaborate by leveraging local computational power and the model's transmission. This method reduces the costs and privacy concerns associated with centralized machine learning methods while ensuring data privacy by distributing training data across heterogeneous devices. On the other hand, federated learning has the drawback of data leakage due to the lack of privacy-preserving mechanisms employed during storage, transfer, and sharing, thus posing significant risks to data owners and suppliers. Blockchain technology has emerged as a promising technology for offering secure data-sharing platforms in federated learning, especially in Industrial Internet of Things (IIoT) settings. This survey aims to compare the performance and security of various data privacy mechanisms adopted in blockchain-based federated learning architectures. We conduct a systematic review of existing literature on secure data-sharing platforms for federated learning provided by blockchain technology, providing an in-depth overview of blockchain-based federated learning, its essential components, and discussing its principles, and potential applications. The primary contribution of this survey paper is to identify critical research questions and propose potential directions for future research in blockchain-based federated learning. The rapid development of the Industrial Internet of Things (IIoT) has resulted in a significant increase in data generated by connected devices [7]. The current privacy and security measures for IIoT are outdated and require significant updates. In addition, some of these measures are still under development and testing with a myriad of vulnerabilities. As a result, new techniques and policies are urgently needed to secure data sharing across wireless networks and address security challenges in IIoT. To address these challenges, Monrat et al. [26] proposes the use of blockchain technology as a secure data-sharing architecture and thus introducing the Blockchain technology as a decentralized and secure IoT revolution. Rao et al. [31] note that user privacy laws in many regions worldwide that mandate technological companies handle user data with extra care. The conventional machine learning techniques have a significant limitation in that they require all data to be gathered in a single location, typically a data center. This approach poses a potential risk to user privacy and could violate data confidentiality laws that protect sensitive information.